TinyTorch

mirror of https://github.com/MLSysBook/TinyTorch.git synced 2026-04-28 16:12:32 -05:00

Files

Vijay Janapa Reddi 1a8e31dce0 Add milestone training examples and fix optimizers

- Created perceptron_trained.py milestone with full training loop
- Restored tinytorch/core/optimizers.py with Optimizer, SGD, Adam, AdamW classes
- Fixed imports to use tinytorch.core.* instead of tensor_dev
- Fixed tinytorch/core/losses.py with all loss functions
- Fixed tinytorch/core/training.py imports

ISSUE: Training loop runs but doesn't learn (gradients not flowing)
- Loss stays constant at 0.7911
- Weights don't update
- Likely autograd (Module 05) backward() not fully implemented
- Need to fix Tensor.backward() and gradient computation

2025-09-30 13:07:53 -04:00

__init__.py

Fix nbdev export system across all 20 modules

2025-09-30 11:21:04 -04:00

activations.py

Fix: Add __call__ methods to exported package files

2025-09-30 12:49:31 -04:00

attention.py

Add exported package files and cleanup

2025-09-30 12:38:56 -04:00

autograd.py

Add exported package files and cleanup